COVID-19 Visualizations

The Data

The data used in this notebook is from the COVID-19 Data Repository by the Center for Systems Science and Engineering (CSSE) at Johns Hopkins University. The package used to retrieve data information can be found here.
Accessed dataset on: 2020-08-11

Preview of Dataset

data("coronavirus")
head(coronavirus)

coronavirus <- coronavirus %>%
  mutate(country = replace(country, country == "US", "United States"))

# Fill empty province with NA
coronavirus$province[coronavirus$province == ""] <- NA

# Population data
library(wpp2019)
data(pop)

keeps <- c("name","2020")
pop_2020 = pop[keeps]
names(pop_2020)[2] <- "population"
pop_2020 <- pop_2020 %>%
  mutate(name = replace(name, name == "United States of America", "United States")) %>%
  mutate(name = replace(name, name == "Iran (Islamic Republic of)", "Iran")) %>%
  mutate(name = replace(name, name == "Russian Federation", "Russia")) %>%
  mutate(name = replace(name, name == "Bolivia (Plurinational State of)", "Bolivia")) %>%
  mutate(name = replace(name, name == "Republic of Moldova", "Moldova")) %>%
  mutate(name = replace(name, name == "Venezuela (Bolivarian Republic of)", "Venezuela"))
pop_2020$population <- pop_2020$population*1000

# add population of each country
cases_pc_df <- left_join(coronavirus, pop_2020, by = c("country" = "name"))

Exploration of Cases Throughout The World

Countries With Highest Cases

Confirmed Case by Country

`summarise()` regrouping output by 'country', 'long', 'lat', 'population' (override with `.groups` argument)

top_10_confirmed_df <- world_confirmed_cases_df[1:10,]

world_confirmed_graph <-
 ggplot(data = top_10_confirmed_df,
        aes(x = reorder(country, total_cases),
            y = total_cases)) +
  labs( x = "Country",
        y = "Total Confirmed Cases",
        title = "Top 10 Countries With Higest Total Confirm Cases") +
  theme(plot.title = element_text(hjust = 0.5),
        axis.text.x = element_text(angle = 45, vjust = 1, hjust = 1)) +
  geom_col(aes(fill = total_cases)) +
  scale_fill_gradient2(low = "thistle1", 
                       high = "mediumorchid1",
                       midpoint = median(top_10_confirmed_df$total_cases)) +
  geom_col(
    aes( y= 40),
    fill = "white",
    width = 1,
    alpha = 0.2,
    size = 0
  ) +
  geom_col(
    aes( y = 20),
    fill = "white",
    width = 1,
    alpha = 0.2,
    size = 0
  )

world_confirmed_graph

Death Cases by Country

world_death_cases_df <- coronavirus %>% 
  filter(type == "death") %>%
  group_by(country, long, lat, province) %>%
  summarise(total_deaths = sum(cases)) %>%
  arrange(-total_deaths)

`summarise()` regrouping output by 'country', 'long', 'lat' (override with `.groups` argument)

top_10_death_df <- world_death_cases_df[1:10,]

world_death_graph <-
 ggplot(data = top_10_death_df, aes(x = reorder(country, total_deaths), y = total_deaths)) +
  geom_col(aes(fill = total_deaths)) +
    labs( x = "Country",
        y = "Total Death Cases",
        title = "Top 10 Countries With Higest Death Cases") +
  theme(plot.title = element_text(hjust = 0.5),
        axis.text.x = element_text(angle = 45, vjust = 1, hjust = 1)) +
  scale_fill_gradient2(low = "red", 
                       high = "red4",
                       midpoint = median(top_10_death_df$total_deaths)) +
  geom_col(
    aes( y= 40),
    fill = "white",
    width = 1,
    alpha = 0.2,
    size = 0
  ) +
  geom_col(
    aes( y = 20),
    fill = "white",
    width = 1,
    alpha = 0.2,
    size = 0
  )

world_death_graph

Recover Cases by Country

world_recovered_cases_df <- coronavirus %>% 
  filter(type == "recovered") %>%
  group_by(country, long, lat, province) %>%
  summarise(total_recovered = sum(cases)) %>%
  arrange(-total_recovered)

`summarise()` regrouping output by 'country', 'long', 'lat' (override with `.groups` argument)

top_10_recovered_df <- world_recovered_cases_df[1:10,]

world_recover_graph <-
 ggplot(data = top_10_recovered_df,
        aes(x = reorder(country, total_recovered),
            y = total_recovered)) +
  geom_col(aes(fill = total_recovered)) +
    labs( x = "Country",
        y = "Total Recovered Cases",
        title = "Top 10 Countries With Higest Total Recovered Cases") +
  theme(plot.title = element_text(hjust = 0.5),
        axis.text.x = element_text(angle = 45, vjust = 1, hjust = 1)) +
  scale_fill_gradient2(low = "green", 
                       high = "green4",
                       midpoint = median(top_10_recovered_df$total_recovered)) +
  geom_col(
    aes( y= 40),
    fill = "white",
    width = 1,
    alpha = 0.2,
    size = 0
  ) +
  geom_col(
    aes( y = 20),
    fill = "white",
    width = 1,
    alpha = 0.2,
    size = 0
  )

world_recover_graph

Timeline

World Confirmed Cases Timeline

world_cases_by_date_df <- coronavirus %>% 
  filter(type == "confirmed") %>%
  group_by(date) %>%
  summarise(total_cases = sum(cases)) %>%
  arrange(-total_cases)

`summarise()` ungrouping output (override with `.groups` argument)

ggplot(world_cases_by_date_df, aes(date, total_cases)) +
  geom_line() +
  labs(x = "Month",
       y = "Cases",
       title ="Cumulative Confirmed Cases Worldwide") +
  theme(plot.title =element_text(hjust = 0.5)) +
  scale_x_date(labels = date_format("%b"), date_breaks = "1 month")

Timeline of Higest Confirmed Cases by Country

# List of countries to include in the graph
country_list <- c("United States", "Brazil", "India", "Russia", "Mexico", "China", "Canada")

top_country_df <- cases_pc_df %>% 
  filter(country %in% country_list) %>%
  filter(type == "confirmed") %>%
  group_by(date, country, population) %>%
  summarise(total_cases = sum(cases)) %>%
  arrange(-total_cases)

`summarise()` regrouping output by 'date', 'country' (override with `.groups` argument)

total_cases <- top_country_df$total_cases
population <- top_country_df$population
top_country_df$`Total Cases` <- total_cases*1000000/population

# draw a line plot of total_cases vs. date, grouped and colored by country
g <- ggplot(data = top_country_df,
            aes(x = date,
                y = `Total Cases`,
                color = country,
                group = country)) +
  geom_line() +
  labs(x= "Month",
       y=" Daily Confirmed Cases per Million People",
       title = "Daily Confirmed Cases by Country (2020)") +
  theme(plot.title = element_text(hjust = 0.5)) +
  scale_x_date(labels = date_format("%b"), date_breaks  ="1 month")

ggly <- ggplotly(p = g,
                 width = 1000,
                 height = 700,
                 tooltip = c("date", "Total Cases", "group"))

`group_by_()` is deprecated as of dplyr 0.7.0.
Please use `group_by()` instead.
See vignette('programming') for more help
This warning is displayed once every 8 hours.
Call `lifecycle::last_warnings()` to see where this warning was generated.

ggly

Worldmap Visualization

# Load packages and world map data
library(sf)
library(tmap)
library(spData)
library(viridis)
library(rnaturalearth)

world <-map_data("world")

breaks<- c(1, 30, 100, 1000, 50000, 100000)
labels<- c("1-29", "20-99", "100-999","1,000-49,999", "50,000-499,999", "100,000+")

confirm_map <- ggplot() +
  geom_polygon(data = world,
               aes(x = long, y = lat, group = group),
               fill = "grey", alpha = 0.3) +
  geom_point(data = world_confirmed_cases_df,
             aes(x = long,
                 y = lat,
                 size = total_cases,
                 color = total_cases,
                 text_country = country,
                 text_province = province,
                 text = paste("Deaths: ", total_cases)),
             alpha = 0.5) +
  scale_size_continuous(name = "Confirmed cases", trans="log", range=c(1,8),
                        breaks = breaks,labels=labels) +
  scale_colour_viridis_c(option = "plasma",
                         direction = -1,
                         name = "Confirmed cases",
                         trans = "log",
                         breaks = breaks,
                         labels = labels) +
  guides(colour=guide_legend()) + 
  theme_void() +
  labs(title = "Map of Confirmed Cases") +
  theme(legend.position="bottom",
        plot.title = element_text(hjust = 0.5))

Ignoring unknown aesthetics: text_country, text_province, text

confirm_map_plotly <- ggplotly(p = confirm_map,
                 width = 1000,
                 height = 700,
                 tooltip = c("text_country", "text_province", "text"))

Transformation introduced infinite values in discrete y-axisTransformation introduced infinite values in discrete y-axisNaNs produced

confirm_map_plotly

breaks<- c(1, 30, 100, 1000, 50000, 100000)
labels<- c("1-29", "20-99", "100-999","1,000-49,999", "50,000-499,999", "100,000+")

death_map <- ggplot() +
  geom_polygon(data = world,
               aes(x = long, y = lat, group = group),
               fill = "grey", alpha = 0.3) +
  geom_point(data = world_death_cases_df,
             aes(x = long,
                 y = lat,
                 size = total_deaths,
                 color = total_deaths,
                 text_country = country,
                 text_province = province,
                 text = paste("Deaths: ", total_deaths)),
             alpha = 0.5) +
  scale_size_continuous(name = "Death cases", trans="log", range=c(1,8),
                        breaks = breaks,labels=labels) +
  scale_colour_viridis_c(option = "inferno",
                         direction = -1,
                         name = "Death cases",
                         trans = "log",
                         breaks = breaks,
                         labels = labels) +
  guides(colour=guide_legend()) + 
  theme_void() +
  labs(title = "Map of Death Cases") +
  theme(legend.position="bottom",
        plot.title = element_text(hjust = 0.5))

Ignoring unknown aesthetics: text_country, text_province, text

death_map_plotly <- ggplotly(p = death_map,
                 width = 1000,
                 height = 700,
                 tooltip = c("text_country", "text_province", "text"))

Transformation introduced infinite values in discrete y-axisTransformation introduced infinite values in discrete y-axisNaNs produced

death_map_plotly

NA